debug

debug is an agent for Claude Code from laurigates/claude-plugins. It costs 27 tokens per session (1,429 once invoked), scanned A, original, MIT.

An agent that investigates software bugs, errors, failures, and unexpected behavior. It looks for the underlying cause, applies a fix, and checks the result.

In plain words
What is it for?
Use it when tests fail, an application behaves unexpectedly, or an error needs to be diagnosed and fixed.
Why use it?
It turns a reported failure into a traced cause and a verified correction instead of leaving the developer to debug it manually.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents; names the TodoWrite tool.

Part of the agents-plugin plugin — 1 skill, 13 agents shipped together

Good fit Use it when tests fail, an application behaves unexpectedly, or an error needs to be diagnosed and fixed.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/laurigates/claude-plugins/debug
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/laurigates/claude-plugins

Made for: Claude Code.

Or install agents-plugin, the plugin that ships this one along with the rest of its 1 skill, 13 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for debug

README.md
[![agentmods](https://agentmods.dev/badge/agents/laurigates/claude-plugins/debug/github.svg)](https://agentmods.dev/agents/laurigates/claude-plugins/debug)
Your own site
<a href="https://agentmods.dev/agents/laurigates/claude-plugins/debug"><img src="https://agentmods.dev/badge/agents/laurigates/claude-plugins/debug/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for debug

Your own site · 80×15
<a href="https://agentmods.dev/agents/laurigates/claude-plugins/debug"><img src="https://agentmods.dev/badge/agents/laurigates/claude-plugins/debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,429 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.01429
Opus 5.5 $0.00011 $0.00572
Sonnet 5.5 $0.00005 $0.00286
Haiku 4.5 $0.00003 $0.00143

Measured 22d ago against content hash 655b3d49f1eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

debug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents-plugin/agents/debug.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debug Agent

Diagnose and fix bugs. This agent finds the root cause, implements the fix, and verifies it works.

Tool Selection

The harness blocks several common bash idioms — use the dedicated tool instead. These rules track measurable friction in agent threads (issue #1109); following them keeps the run fast and avoids hook-block round-trips.

Avoid Use instead
find . -name '*.ts' Glob(pattern="**/*.ts")
grep -r 'foo' src/ Grep(pattern="foo", path="src", -r=true)
cat/head/tail on a file Read — use offset/limit to page through
echo ... > file / cat > file Write(file_path=..., content=...)
git add . / git add -A git add <explicit-paths> — protects unrelated coworker changes
git add ... && git commit ... Two separate Bash calls — git's index.lock does not survive &&

Read before Edit/Write. The harness tracks read-state per agent thread. Read every file in the current thread before editing or writing it — the parent session's Read does not count. If a formatter, linter, or hook may have rewritten a file since you read it, Read again before the next Edit.

Scope

  • Input: Bug description, error message, failing test, or unexpected behavior
  • Output: Fixed code, verification that issue is resolved
  • Steps: 5-15, completes the fix

Checkpoint Discipline

Investigations that span multiple files or take many tool uses can exhaust context mid-task (issue #1390). If you sense the response is getting long — many reads, complex edits, repeated test runs — commit work-in-progress before continuing:

  1. Stage what's done with explicit paths: git add <path1> <path2> (never -A or .)
  2. Commit as a separate Bash call: git commit -m "wip: <description> — checkpoint" (do not chain with &&)
  3. Continue with the next step

A checkpoint commit makes the investigation recoverable if context exhausts. The orchestrator can rebase or squash checkpoints into the final commit. Checkpoint after each of:

Read the full file on GitHub · 148 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 22d ago Changed 655b3d49f1eb
  2. 1mo ago Changed · +4 lines f677cbed9fdd
  3. 1mo ago First seen · 144 lines · 27 tokens per session scan A 094c447f2703

Subscribe to this mod's changes

debug is an agent published in the GitHub repository laurigates/claude-plugins (60 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 1,429 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

verifier

Runs the app, exercises changed behaviour and the flows next to it, and reports what actually worked. Use after implementing a change and before showing it to a human. Reports only - it never fixes anything.

artemnovichkov/skills · 44 tokens

debugger

Use this agent to diagnose and fix bugs from error messages, stack traces, or unexpected behavior. Traces root causes through the codebase, checks recent changes, and proposes minimal fixes. Examples: User: "I'm getting a TypeError in the dashboard" Assistant: "I'll launch the debugger agent to trace the root cause."…

Sagargupta16/claude-skills · 99 tokens

backend-analyzer

Analyze backend services, business logic, and server-side code for inefficient algorithms, blocking operations, or unnecessary computations. Use when user asks about backend performance or runs /n1-optimizer:analyze.

hculap/better-code · 44 tokens

therapist

Audits and rewrites error messages to be helpful and actionable. Use when reviewing error handling code, improving user experience, or standardizing error messages across a codebase. PROACTIVELY USE when you see poor error messages.

jimmc414/claude-code-plugin-marketplace · 50 tokens

debugger

Debugging and troubleshooting specialist for Rust and TypeScript projects focused on systematic error diagnosis, interactive debugger sessions, panic and exception analysis, async debugging, memory issues, and production incident investigation. Applies the project's language rules from the stack profile. Use…

bug-ops/claude-plugins · 78 tokens

the-postmortem-facilitator

Use after any significant engineering incident to facilitate a blameless postmortem—timeline reconstruction, root cause analysis, action item discipline. Trigger when the user says "we had an incident", "we need to run a postmortem", "the outage is over — now what?", or "how do I run a blameless retrospective on…

shrwnsan/vibekit-claude-plugins · 99 tokens